lucataco / ssd-1b

Segmind Stable Diffusion Model (SSD-1B) is a distilled 50% smaller version of SDXL, offering a 60% speedup while maintaining high-quality text-to-image generation capabilities

Cold

Public
995.8K runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

with smoke, half ice and half fire and ultra realistic in detail.wolf, typography, dark fantasy, wildlife photography, vibrant, cinematic and on a black backgroundwith smoke, half ice and half fire and ultra realistic in detail.wolf, typography, dark fantasy, wildlife photography, vibrant, cinematic and on a black background

Input prompt

Default: "with smoke, half ice and half fire and ultra realistic in detail.wolf, typography, dark fantasy, wildlife photography, vibrant, cinematic and on a black background"

negative_prompt

string

Shift + Return to add a new line

Negative Input prompt

Default: "scary, cartoon, painting"

batched_prompt

boolean

When active, your prompt will be split by newlines and images will be generated for each individual line

Default: false

image

file

Input image for img2img or inpaint mode

mask

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

width

integer

Width of output image

Default: 768

height

integer

Height of output image

Default: 768

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "K_EULER"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 25

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

seed

integer

Random seed. Leave blank to randomize the seed

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety

Default: false

Run this model in Node.js with one line of code:

npx create-replicate --model=lucataco/ssd-1b

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/ssd-1b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/ssd-1b:b19e3639452c59ce8295b82aba70a231404cb062f2eb580ea894b31e8ce5bbb6",
  {
    input: {
      seed: 36446545872,
      width: 768,
      height: 768,
      prompt: "with smoke, half ice and half fire and ultra realistic in detail.wolf, typography, dark fantasy, wildlife photography, vibrant, cinematic and on a black background",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      batched_prompt: false,
      guidance_scale: 9,
      apply_watermark: true,
      negative_prompt: "scary, cartoon, painting",
      prompt_strength: 0.8,
      num_inference_steps: 25
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run lucataco/ssd-1b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/ssd-1b:b19e3639452c59ce8295b82aba70a231404cb062f2eb580ea894b31e8ce5bbb6",
    input={
        "seed": 36446545872,
        "width": 768,
        "height": 768,
        "prompt": "with smoke, half ice and half fire and ultra realistic in detail.wolf, typography, dark fantasy, wildlife photography, vibrant, cinematic and on a black background",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "batched_prompt": False,
        "guidance_scale": 9,
        "apply_watermark": True,
        "negative_prompt": "scary, cartoon, painting",
        "prompt_strength": 0.8,
        "num_inference_steps": 25
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run lucataco/ssd-1b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "b19e3639452c59ce8295b82aba70a231404cb062f2eb580ea894b31e8ce5bbb6",
    "input": {
      "seed": 36446545872,
      "width": 768,
      "height": 768,
      "prompt": "with smoke, half ice and half fire and ultra realistic in detail.wolf, typography, dark fantasy, wildlife photography, vibrant, cinematic and on a black background",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "batched_prompt": false,
      "guidance_scale": 9,
      "apply_watermark": true,
      "negative_prompt": "scary, cartoon, painting",
      "prompt_strength": 0.8,
      "num_inference_steps": 25
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-12-06T21:08:18.042372Z",
  "created_at": "2024-12-06T21:08:16.635000Z",
  "data_removed": false,
  "error": null,
  "id": "7n0h7128fdrma0ckkq6rphkkn4",
  "input": {
    "seed": 36446545872,
    "width": 768,
    "height": 768,
    "prompt": "with smoke, half ice and half fire and ultra realistic in detail.wolf, typography, dark fantasy, wildlife photography, vibrant, cinematic and on a black background",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "batched_prompt": false,
    "guidance_scale": 9,
    "apply_watermark": true,
    "negative_prompt": "scary, cartoon, painting",
    "prompt_strength": 0.8,
    "num_inference_steps": 25
  },
  "logs": "Using seed: 36446545872\nPrompt: with smoke, half ice and half fire and ultra realistic in detail.wolf, typography, dark fantasy, wildlife photography, vibrant, cinematic and on a black background\ntxt2img mode\n  0%|          | 0/25 [00:00<?, ?it/s]\n  8%|▊         | 2/25 [00:00<00:01, 17.04it/s]\n 20%|██        | 5/25 [00:00<00:00, 22.00it/s]\n 32%|███▏      | 8/25 [00:00<00:00, 23.40it/s]\n 44%|████▍     | 11/25 [00:00<00:00, 24.11it/s]\n 56%|█████▌    | 14/25 [00:00<00:00, 24.51it/s]\n 68%|██████▊   | 17/25 [00:00<00:00, 24.73it/s]\n 80%|████████  | 20/25 [00:00<00:00, 24.86it/s]\n 92%|█████████▏| 23/25 [00:00<00:00, 24.92it/s]\n100%|██████████| 25/25 [00:01<00:00, 24.23it/s]",
  "metrics": {
    "predict_time": 1.398281685,
    "total_time": 1.407372
  },
  "output": [
    "https://replicate.delivery/xezq/22omflc90SUAI6J8R2tioVJYeDq1oYO8XrDYrUYzeF8FOjwnA/out-0.png"
  ],
  "started_at": "2024-12-06T21:08:16.644090Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-ap226x5vfp2teztlqgnawxm5e3nhg5breye7rkwsfxb7aoflzhta",
    "get": "https://api.replicate.com/v1/predictions/7n0h7128fdrma0ckkq6rphkkn4",
    "cancel": "https://api.replicate.com/v1/predictions/7n0h7128fdrma0ckkq6rphkkn4/cancel"
  },
  "version": "b19e3639452c59ce8295b82aba70a231404cb062f2eb580ea894b31e8ce5bbb6"
}

Generated in

1.4 seconds

Tweak it Share Report

Examples

View more examples

Run time and cost

This model costs approximately $0.019 to run on Replicate, or 52 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 20 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Model Description

The Segmind Stable Diffusion Model (SSD-1B) is a distilled 50% smaller version of the Stable Diffusion XL (SDXL), offering a 60% speedup while maintaining high-quality text-to-image generation capabilities. It has been trained on diverse datasets, including Grit and Midjourney scrape data, to enhance its ability to create a wide range of visual content based on textual prompts.

This model employs a knowledge distillation strategy, where it leverages the teachings of several expert models in succession, including SDXL, ZavyChromaXL, and JuggernautXL, to combine their strengths and produce impressive visual outputs.

Special thanks to the HF team 🤗 especially Sayak, Patrick and Poli for their collaboration and guidance on this work.

@article{kim2023architectural,
  title={On Architectural Compression of Text-to-Image Diffusion Models},
  author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
  journal={arXiv preprint arXiv:2305.15798},
  year={2023},
  url={https://arxiv.org/abs/2305.15798}
}